Founding Engineer
Apply for this roleAbout the role
As a Founding Engineer, you will help build the core of a platform that sits at the layer most AI applications depend on. Inferbase classifies each request and routes it to the model that fits best on quality, cost, and latency, then serves it through one OpenAI-compatible API. You will own the systems that make this work, including the routing engine, the inference serving path, billing and settlement, and the developer-facing API.
Because the team is small and senior, the role is broad and the decisions carry weight. The architecture you choose, the reliability bar you set, and the systems you build will shape how Inferbase scales. You will work directly with the founders and with early customers, and move quickly from a problem to something running in production.
What you will do
- Design, build, and operate core systems across the backend and infrastructure, including the routing engine, the inference serving path, billing and settlement, and the public API.
- Own systems from design through production, monitoring, and on-call, taking responsibility for both the code and how it behaves under real traffic.
- Make architecture decisions that solve the current problem without constraining the product as usage grows, and revisit them with evidence as the system scales.
- Hold a high bar on the money and data paths, where correctness matters most, through review, testing, and instrumentation.
- Work with early customers to understand their needs, debug integrations, and turn what you learn into shipped improvements.
- Contribute across the stack when it helps, including the frontend and developer experience, rather than staying within a single layer.
- Help establish the team engineering practices and tooling, and help interview and onboard the engineers who follow.
You may be a good fit if you have
- Five or more years building and operating production backend systems that people rely on.
- Depth in a modern backend stack such as Python with FastAPI or Go, together with strong SQL and PostgreSQL experience.
- Experience with distributed systems, reliability, and performance under real load.
- A habit of taking an ambiguous problem and driving it to something shipped and operated, without waiting for detailed direction.
- Comfort with the shifting priorities of an early-stage team, and the judgment to know when to build for now and when to build for later.
- Clear written and verbal communication, since you will work closely with the founders, customers, and future teammates.
- Familiarity with large language model (LLM) or inference infrastructure, model serving, or API gateways is useful but not required.
- Experience with payments or other correctness-critical systems, and with Next.js and TypeScript, is a plus.
We encourage you to apply even if you do not meet every point above. Strong candidates rarely match a list exactly, and people from underrepresented groups are more likely to rule themselves out early. If the work interests you, we would rather read your application than have you hold back.
Apply for this role
Start building with smart routing.
Automatically route workloads to the right model for every task, every time.